Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/cleanunicorn/earheart/agents-mdgit clone --depth 1 https://github.com/cleanunicorn/earheartWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01703 | $0.01703 |
| Opus 5 | $0.00851 | $0.00851 |
| Sonnet 5 | $0.00341 | $0.00341 |
| Haiku 4.5 | $0.00170 | $0.00170 |
Grade A, and why
earheart AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents (and humans) contributing to Earheart. This project
follows the GitHub flow: main is always releasable, all work happens on
short-lived branches, and every change lands through a reviewed pull request.
Read CONTRIBUTING.md for full setup, build, and architecture details. This file is the operational checklist for how to work here.
Golden rules
- Never commit directly to
main. It is protected and is the release branch — merging to it auto-publishes a release (see below). Always branch. - Never push to
mainor force-push a shared branch. - The PR title is load-bearing. It drives the released version bump, so it must be a valid Conventional Commits string (see PR titles).
- Keep
maingreen. Run the checks locally before opening a PR. - Never lose the user's words. A core design constraint of the app — if you touch the pipeline, preserve the raw-transcript fallbacks.
The GitHub flow, step by step
1. Start from an up-to-date main
git checkout main
git pull origin main
2. Create a branch
Branch names are short, lowercase, hyphenated, and prefixed by intent. Match the Conventional Commits type you expect the PR to use:
feat/<short-description> # new feature
fix/<short-description> # bug fix
refactor/<short-description> # internal change, no behavior change
docs/<short-description> # documentation only
chore/<short-description> # tooling, deps, housekeeping
Examples: feat/overlay-copy-button, fix/windows-autostart-readback,
docs/agents-guide.
git checkout -b fix/windows-autostart-readback
3. Make focused changes
- One logical change per PR. Don't bundle an unrelated refactor into a fix.
- Match the surrounding style: plain JavaScript, no bundler, few runtime deps. Stay close to Electron built-ins and platform tools rather than adding npm packages — the only runtime deps are the two native engines.
- Keep diffs small and reviewable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 182 lines · 1,703 tokens per session scan A 8d6581698059
earheart AGENTS.md is an instructions file published in the GitHub repository cleanunicorn/earheart (22 stars, last pushed 4d ago), licensed MIT. It adds 1,703 tokens to every session, about $0.0085 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
chat-on-steroids AGENTS.md
Instructions for totec448-spec/chat-on-steroids, covering chat on steroids — the agent map, 1. the app in sixty seconds, 2. where the bugs actually are, name the identity, then find where it is lost and 3. what is authoritative.
chat-on-steroids CLAUDE.md
Instructions for totec448-spec/chat-on-steroids: Read and follow AGENTS.md before changing this repository.
snip CLAUDE.md
Instructions for rixinhahaha/snip, covering claude.md — autonomous agent instructions, role documents, documentation rules, how to update and critical constraints.
vscode tree-widgets.instructions.md
Use when asked to consume workbench tree widgets in VS Code.
vscode accessibility.instructions.md
Use when implementing accessibility features, ARIA labels, screen reader support, accessible help dialogs, or keybinding scoping for accessibility. Covers AccessibleContentProvider, CONTEXTACCESSIBILITYMODEENABLED, verbosity settings, and announcement patterns.
vscode source-code-organization.instructions.md
VS Code source code organization — layers, target environments, dependency injection, and folder structure conventions. Reference when adding new modules, services, or contributions.